MCPs › cold-run
Enables you to audit your AI agent skills by running each one against an agent that cannot see it, diffing the resulting artifacts, and grading whether each skill genuinely improves, changes nothing, or worsens the output.
Not monetized yet
Turn cold-run’s tool calls into revenue: one disclosed sponsored slot, 70% revenue share, fail-open by design.
Install cold-run
For anyone using cold-run — no Lulu account needed# stdio server — install per the repository README: https://github.com/sina-heidariaan/cold-run
Real-time weather for any city, built on the lulu-ads widget gallery. First-party, free forever.
View server →FAQ
cold-run installs from source — follow the repository README.
Unrated out of 100, computed from cross-registry traction signals (installs, stars, registry presence) — never influenced by sponsorship.
Similar servers
Your server?
This is for the person who owns cold-run — adds Lulu Ads to your own code. Not the install steps above, those are for your users.
Copies a ready prompt: your coding agent installs the lulu-ads SDK, wires the slot, and applies the widget design guide.
or set up manually at getlulu.dev/publishers
Get verified so you can edit the page. Your badge is already live below — no claim needed for that.
Managed hosting with monetization built in — waitlist.
[](https://getlulu.dev/mcps/cold-run)